{"id":"https://openalex.org/W2972686346","doi":"https://doi.org/10.1109/icassp.2019.8683859","title":"Investigation of Modeling Units for Mandarin Speech Recognition Using Dfsmn-ctc-smbr","display_name":"Investigation of Modeling Units for Mandarin Speech Recognition Using Dfsmn-ctc-smbr","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2972686346","doi":"https://doi.org/10.1109/icassp.2019.8683859","mag":"2972686346"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058896884","display_name":"Ming Lei","orcid":"https://orcid.org/0000-0002-5712-3285"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Lei","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390839","display_name":"Yuan Liu","orcid":"https://orcid.org/0000-0002-0246-0778"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Liu","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100318020","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7824-4839"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101777591"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":3.7804,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94777786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7085","last_page":"7089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991111874580383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7931042313575745},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7575495839118958},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7312162518501282},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6466271281242371},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5935708284378052},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5445119142532349},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5203706622123718},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4617929458618164},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4193611443042755},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4186871647834778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4181070029735565},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39895927906036377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06870704889297485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991111874580383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7931042313575745},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7575495839118958},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7312162518501282},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6466271281242371},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5935708284378052},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5445119142532349},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5203706622123718},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4617929458618164},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4193611443042755},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4186871647834778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4181070029735565},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39895927906036377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06870704889297485},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1533416326","https://openalex.org/W1533861849","https://openalex.org/W1571745681","https://openalex.org/W1893226766","https://openalex.org/W1922655562","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2114016253","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2147768505","https://openalex.org/W2193413348","https://openalex.org/W2208299922","https://openalex.org/W2405883473","https://openalex.org/W2407648438","https://openalex.org/W2515439472","https://openalex.org/W2590320937","https://openalex.org/W2888226713","https://openalex.org/W2889068726","https://openalex.org/W2963211739","https://openalex.org/W2963308316","https://openalex.org/W2963920996","https://openalex.org/W2963970535","https://openalex.org/W2964084166","https://openalex.org/W6629052376","https://openalex.org/W6629930100","https://openalex.org/W6631943919","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6688039610","https://openalex.org/W6713982112","https://openalex.org/W6753776127"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W27484908","https://openalex.org/W2163874654","https://openalex.org/W2061937230","https://openalex.org/W2132658536"],"abstract_inverted_index":{"The":[0,19],"choice":[1,33,119],"of":[2,34,95,162,166],"acoustic":[3,9,26,44,123],"modeling":[4,10,35,49,75,96,114,124],"units":[5,50,76,97,115],"is":[6,116,171],"critical":[7],"to":[8,57],"in":[11,129,139],"large":[12],"vocabulary":[13],"continuous":[14],"speech":[15,53,127,147],"recognition":[16,128,140,148],"(LVCSR)":[17],"tasks.":[18],"recent":[20],"connectionist":[21],"temporal":[22],"classification":[23],"(CTC)":[24],"based":[25,122],"models":[27,90],"have":[28],"more":[29],"options":[30],"for":[31,51,120,125],"the":[32,58,101,110,117,150,167],"units.":[36],"In":[37,55,142],"this":[38],"work,":[39],"we":[40,69,107],"propose":[41,71],"a":[42,72,143,157],"DFSMN-CTC-sMBR":[43,89,151],"model":[45],"and":[46,67,83],"investigate":[47],"various":[48],"Mandarin":[52,126,146],"recognition.":[54],"addition":[56],"commonly":[59],"used":[60],"context-independent":[61],"Initial/Finals":[62,65],"(CI-IF),":[63],"context-dependent":[64],"(CD-IF)":[66],"Syllable,":[68],"also":[70],"hybrid":[73,104,112,154],"Character-Syllable":[74,113,155],"by":[77],"mixing":[78],"high":[79],"frequency":[80],"Chinese":[81],"characters":[82],"syllables.":[84],"Experimental":[85],"results":[86],"show":[87],"that":[88,109],"with":[91,153],"all":[92],"these":[93],"types":[94],"can":[98,134],"significantly":[99],"outperform":[100],"well-trained":[102,168],"conventional":[103],"models.":[105],"Moreover,":[106],"find":[108],"proposed":[111],"best":[118],"CTC":[121],"our":[130],"work":[131],"since":[132],"it":[133],"dramatically":[135],"reduce":[136],"substitution":[137],"errors":[138],"results.":[141],"20,000":[144],"hours":[145],"task,":[149],"system":[152,170],"achieves":[156],"character":[158],"error":[159],"rate":[160],"(CER)":[161],"7.45%":[163],"while":[164],"performance":[165],"DFSMN-CE-sMBR":[169],"9.49%.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}